Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Leflunomide-inhibited STAT1 activity ameliorates intramuscular M1 macrophage infiltration and promotes muscle regeneration in Duchenne muscular dystrophy.

British journal of pharmacology·2026
Same author

High-throughput machine learning-aided antibody discovery for cell surface antigens.

Cell systems·2026
Same author

Cross-frequency bispectral EEG analysis of reach-to-grasp planning and execution.

Computers in biology and medicine·2026
Same author

A High-Performance Solid-State Secondary Battery Using a Triple-Phase-Interface Anode Displaying Excellent Capacity and Electrochemical Kinetics.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Beyond Hyperfluorescence: Leveraging a Host-Guest Exciplex to Significantly Suppress the Efficiency Roll-Off and Improve the Operational Stability in Narrowband Emissive Devices.

Angewandte Chemie (International ed. in English)·2026
Same author

Impact of Vitamin D3 Supplementation on 28-Day ICU Mortality in Sepsis Patients: A Retrospective Study with Propensity Score Matching.

Pathogens (Basel, Switzerland)·2026

Related Experiment Video

Updated: Aug 14, 2025

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.2K

A dynamical graph-based feature extraction approach to enhance mental task classification in brain-computer

Shaotong Zhu1, Sarah Ismail Hosni2, Xiaofei Huang1

  • 1The Department of Electrical and Computer Engineering, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA.

Computers in Biology and Medicine
|January 12, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel graph-based feature framework for brain-computer interfaces (BCIs), improving mental task classification accuracy in individuals with ALS by analyzing electroencephalogram (EEG) signals.

Keywords:
Brain–computer interfaces (BCI)Feature selectionGraph theoryMental task classification

More Related Videos

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

945
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.5K

Related Experiment Videos

Last Updated: Aug 14, 2025

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.2K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

945
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.5K

Area of Science:

  • Neuroscience
  • Graph Theory
  • Biomedical Engineering

Background:

  • Brain-computer interfaces (BCIs) often use electroencephalogram (EEG) signals.
  • Current BCIs frequently overlook topological information within EEG temporal dynamics.
  • Existing graph theory applications in neuroscience primarily focus on spatial functional networks, not temporal interdependencies.

Purpose of the Study:

  • To develop and evaluate a robust framework using graph-based and spectral graph features for BCI applications.
  • To investigate the discriminative performance of this framework for classifying mental tasks in individuals with amyotrophic lateral sclerosis (ALS).

Main Methods:

  • A novel fold-wise hyperparameter optimization framework was implemented.
  • Conventional graph-based measurements and spectral graph features were combined.
  • The framework was tested on EEG data from 6 participants with ALS performing a designed mental task.

Main Results:

  • The combined graph-based and spectral graph features achieved an average accuracy of 71.1%±4.5% for mental task classification.
  • This performance surpassed conventional non-graph based features (67.1%±7.5%) and individual graph feature sets (eigenvalues: 66.3%±6.5%; global graph features: 65.9%±5.2%).
  • The feature combination strategy demonstrated significant improvements in both accuracy and robustness.

Conclusions:

  • The presented fold-wise optimization framework utilizing graph-based features is feasible and advantageous for BCI systems.
  • This approach enhances the analysis of spatiotemporal brain dynamics for improved BCI performance in end-users.